Upload 12 files

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "h",
+    "1": "pp",
+    "2": "qq"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "h": 0,
+    "pp": 1,
+    "qq": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e873c3f5dae1008bc6efdc8f413b1571eb3d89f4018b22a402479ce4b01743e6
+size 1421499516

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb96657e5afb4f31cd65a7563b19cdad9a106c9fa4701a12c1c67cddc6b2dc2c
+size 2843231469

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1508b175b79c75a88d5f7f2a56e937c14c8f9189ac39d68d69b4fe7241feae8
+size 14180

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3e199bbda9aad4143a96ea0ac9ce1bd6d44218caf1398e9109759bd9461ed0
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 1.0,
+  "best_model_checkpoint": "train_authorship/train_outputs/05-21-2024_13:13:45/checkpoint-6",
+  "epoch": 2.5,
+  "eval_steps": 2,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.089840412139893,
+      "learning_rate": 2.5e-05,
+      "loss": 1.1456,
+      "step": 2
+    },
+    {
+      "epoch": 0.5,
+      "eval_acc_product": 0.0,
+      "eval_h_acc": 0.7692307692307693,
+      "eval_loss": 1.0893480777740479,
+      "eval_overall_acc": 0.5897435897435898,
+      "eval_pp_acc": 1.0,
+      "eval_qq_acc": 0.0,
+      "eval_runtime": 0.2361,
+      "eval_samples_per_second": 165.177,
+      "eval_steps_per_second": 4.235,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.872375965118408,
+      "learning_rate": 5e-05,
+      "loss": 1.12,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "eval_acc_product": 0.1301775147928994,
+      "eval_h_acc": 0.8461538461538461,
+      "eval_loss": 1.0048478841781616,
+      "eval_overall_acc": 0.6666666666666666,
+      "eval_pp_acc": 0.15384615384615385,
+      "eval_qq_acc": 1.0,
+      "eval_runtime": 0.2352,
+      "eval_samples_per_second": 165.814,
+      "eval_steps_per_second": 4.252,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.280738830566406,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.9317,
+      "step": 6
+    },
+    {
+      "epoch": 1.5,
+      "eval_acc_product": 1.0,
+      "eval_h_acc": 1.0,
+      "eval_loss": 0.4365764558315277,
+      "eval_overall_acc": 1.0,
+      "eval_pp_acc": 1.0,
+      "eval_qq_acc": 1.0,
+      "eval_runtime": 0.2356,
+      "eval_samples_per_second": 165.51,
+      "eval_steps_per_second": 4.244,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.260248184204102,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.3742,
+      "step": 8
+    },
+    {
+      "epoch": 2.0,
+      "eval_acc_product": 1.0,
+      "eval_h_acc": 1.0,
+      "eval_loss": 0.09832292050123215,
+      "eval_overall_acc": 1.0,
+      "eval_pp_acc": 1.0,
+      "eval_qq_acc": 1.0,
+      "eval_runtime": 0.2365,
+      "eval_samples_per_second": 164.897,
+      "eval_steps_per_second": 4.228,
+      "step": 8
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 3.575946807861328,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.1006,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "eval_acc_product": 1.0,
+      "eval_h_acc": 1.0,
+      "eval_loss": 0.011917746625840664,
+      "eval_overall_acc": 1.0,
+      "eval_pp_acc": 1.0,
+      "eval_qq_acc": 1.0,
+      "eval_runtime": 0.2364,
+      "eval_samples_per_second": 164.977,
+      "eval_steps_per_second": 4.23,
+      "step": 10
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 2,
+  "total_flos": 190740783974448.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341a94260346a9cd04bb1b76b2f75d7df3df564fee684d0d747abb6aa98713bd
+size 4920